Nikhil Sapre Tejas Puntambekar INTRODUCTION • • • • • • • The Need Types Working Examples Research Objectives and Challenges Near Future References Background Image Courtesy Dawid Michalczyk http://www.art.eonworks.com/gallery/concept/concept_gallery_1.html Why Military Robots? • Job of Soldier is no walk in the PARK • Difficult Tasks – Walking through minefields – deactivating unexploded bombs – clearing out hostile buildings • Robots to do these jobs instead of humans • To operate in a relatively unstructured, natural environment • Replacing human in dangerous, dirty, or dull missions • Bear cost to build the robot instead of losing a human life http://science.howstuffworks.com/military-robot.htm TYPES • Today's military robots don't do a whole lot on their own. • Computer brains aren't very sophisticated in terms of artificial intelligence (AI). • Instead of independent AI, most military robots are remote-controlled by human operators. Hence the term Unmanned Vehicles • UAV – Unmanned Aerial Vehicle • UUV – Unmanned Underwater Vehicle • UGV – Unmanned Ground Vehicles http://science.howstuffworks.com/military-robot.htm Examples MQ1-Predator TALON Talisman MULE A UTONOMOUS ROB OTS BIGDOG CRUSHER Basic Idea • The basic idea is to program the robot to respond a certain way to outside stimuli. • Most of them use stereo vision to see the world around them. Several Cameras give these robots depth perception, and image-recognition software gives them the ability to locate and classify various objects. • More advanced robots can analyze and adapt to unfamiliar environments, even to areas with rough terrain. These robots may associate certain terrain patterns with certain actions. A rover robot, for example, might construct a map of the land in front of it based on its visual sensors. If the map shows a very bumpy terrain pattern, the robot knows to travel another way. B I G • Developed by Boston Dynamics • Quadruped robot – – – – Walk Run Climbs on rough terrain Carries heavy loads. • Legs contain sensors, including joint position and ground contact. • BigDog also features a laser gyroscope and a stereo vision system. • On-board computer controls locomotion, servos the legs and handles a wide variety of sensors. • Big Dog's control system manages the dynamics of its behavior to keep it balanced, steer and navigate D O G CRUSHER • UGV Funded by DARPA and designed by Carnegie Mellon’s National Robotics Engineering Center (NREC). • Designed primarily for - Reconnaissance and Support . • Key Features :- Rugged, flexible vehicle that can carry huge payloads. Navigate autonomously over extreme terrain. Runs on battery power alone - silent operation. Can carry weapons - Combat roles down the line. WORKING • 78hp turbo-diesel engine – GENERATOR. • Output - continuous 58 kW power. • Charges Crusher's 300-volt, 18.7-kW, lithium-ion battery pack. • The batteries in turn run six 210-kW electric motors(Each produces 282 hp). • Regenerative Braking. Vision • 8 LADAR units(4h,4v) - scan area and measures ‘t’ for the REFLECTED beam. 6 pairs of stereo-vision cameras - depth perception . 4 color cameras - apply a color pixel to each point of distance determined by the LADAR sensor. ON-BOARD CPU(700-MHz Pentium 3) Creates a 3-D picture of the landscape in which Crusher is traveling. controls mechanical activities and runs the navigation software . INERTIAL MEASUREMENT UNIT (IMU) Detects Crusher's altitude, position and direction of movement. Combination of accelerometers (tilt sensors) and gyroscopes. So Crusher is always aware of its own motion and position relative to the landscape. SPECIFICATIONS Empty vehicle weight: 13,200 lbs (5,990 kg) Maximum payload: 8,000 lbs (3,600 kg) Length: 201 inches (510 cm) Width: 102 inches (260 cm) Height :60 inches (152 cm) Ground clearance: 0 to 30 inches (76 cm) Tire diameter: 49.5 inches (125.7 cm) Top speed: 26 mph (42 kph) in 7 sec Possible control modes: • • • Remote control Waypoint-based navigation Full autonomy Research Objectives • Interacting with computation should be as natural as interacting with people • Human-like interfaces need to be: – modality-opportunistic – mixed-initiative – multi-lingual • Military “robots” today lack autonomy – Currently, many soldiers operate one robot – Want few soldiers working with a team of agile robots, to achieve force multiplication even in harsh environments – Put fewer soldiers in harm’s way • Better robots for monitoring – Enable soldiers with persistent and pervasive Intelligence, Surveillance, and Reconnaissance (ISR), including from hard to reach • Better robots for logistics – Replace soldiers in the supply chain with capable autonomous robots and vehicles MIT Computer Science and Artificial Intelligence Laboratory Research Challenges • Reliance on centrally derived information may lead to significant problems. • Objects in the environment should be basic building blocks of the robot operator for world • Time for robotic planning (path planning, task planning, and mission planning) • The operator has significant and well-defined roles to play even if the robots are highly autonomous, and the robot and user interfaces must support these roles. • Avoid lethal crossfire situation • Utilize local information and not rely on a global source • To navigate in complex indoor or outdoor environments and build three-dimensional models for manipulation. Research Challenges • Robust, secure communication links • Safe, long duration, lightweight, power storage • Perception for real-world navigation and for mission operations • Approach the performance of a human in performing dexterous manipulation of tools, weapons. • Performing real-time diagnosis and recovery from anomalous conditions • Keeping the system safe Near Future • EXOSKELETON References Journals – AUTONOMOUS ROBOTS FOR MILITARY SYSTEMS(ARMS) - Surya P. N. Singh and Scott M. Thayer Carnegie Mellon University – The First Law of Military Robotics: Avoid Collateral Damage – Autonomous Robots in SWAT Applications: Research, Design, and Operations Challenges – Stanford University – Research Challenges for the Next Decade –MIT Computer Science and Artificial Intelligence Laboratory Websites http://www.2dayblog.com/images/060409_robot_sherpa_02.jpg • http://science.howstuffworks.com/military-robot.htm • http://science.howstuffworks.com/robot6.htm# • http://science.howstuffworks.com/future-military-technology.htm • http://usmilitary.about.com/cs/weapons/a/robots.htm • http://www.wtec.org/robotics/us_workshop/ • http://www.art.eonworks.com/about/about.html • http://www.gizmohighway.com/robotics/talon_robot.htm • http://brainstuff.howstuffworks.com/2008/02/26/the-crusher-robot-vehicle/ • http://science.howstuffworks.com/crusher1.htm • http://usmilitary.about.com/od/armyweapons/a/crusher.htm • http://www.telegraph.co.uk/news/worldnews/northamerica/usa/2687038/Robotic-BigDog-is-US-armys-best• friend.html !! THANK YOU !! Nikhil Sapre Tejas Puntambekar
